{"id":105165,"date":"2022-09-25T21:36:38","date_gmt":"2022-09-25T19:36:39","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper"},"modified":"2022-09-25T21:36:38","modified_gmt":"2022-09-25T19:36:39","slug":"otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hu\/blog\/news\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","title":{"rendered":"Megny\u00edlt a Whisper besz\u00e9dfelismer\u0151 \u00e9s ford\u00edt\u00f3 rendszer k\u00f3dja","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Az OpenAI projektje, amely ny\u00edlt hozz\u00e1f\u00e9r\u00e9s\u0171 mesters\u00e9ges intelligencia projektek fejleszt\u00e9s\u00e9vel foglalkozik, k\u00f6zz\u00e9tette a Whisper hangfelismer\u0151 rendszerhez kapcsol\u00f3d\u00f3 munk\u00e1it. Azt \u00e1ll\u00edtj\u00e1k, hogy az angol nyelv\u0171 besz\u00e9d eset\u00e9ben a rendszer megb\u00edzhat\u00f3s\u00e1gi \u00e9s pontoss\u00e1gi szintje k\u00f6zel \u00e1ll ahhoz, amit az emberi besz\u00e9d felismer\u00e9se ny\u00fajt. A referencia megval\u00f3s\u00edt\u00e1s k\u00f3dja a PyTorch keretrendszer alapj\u00e1n nyitott, \u00e9s m\u00e1r el\u00e9rhet\u0151 el\u0151k\u00e9pzett modellek is rendelkez\u00e9sre \u00e1llnak. A k\u00f3d MIT licenc alatt \u00e9rhet\u0151 el. <\/p>\n

A modell k\u00e9pz\u00e9s\u00e9hez 680 000 \u00f3r\u00e1nyi besz\u00e9dadatot haszn\u00e1ltak fel, amelyeket t\u00f6bb gy\u0171jtem\u00e9nyb\u0151l gy\u0171jt\u00f6ttek \u00f6ssze, k\u00fcl\u00f6nb\u00f6z\u0151 nyelveket \u00e9s t\u00e9m\u00e1kat lefedve. Az oktat\u00e1shoz felhaszn\u00e1lt besz\u00e9dadatok k\u00f6r\u00fclbel\u00fcl 1\/3-a olyan nyelvekhez tartozik, amelyek elt\u00e9rnek az angolt\u00f3l. A javasolt rendszer helyesen kezeli az olyan helyzeteket, mint a kiejt\u00e9s akcentussal, h\u00e1tt\u00e9rzajok jelenl\u00e9te \u00e9s technikai zsARGON haszn\u00e1lata. A besz\u00e9d sz\u00f6vegg\u00e9 val\u00f3 \u00e1t\u00edr\u00e1sa mellett a rendszer k\u00e9pes a besz\u00e9det tetsz\u0151leges nyelvr\u0151l angolra ford\u00edtani \u00e9s azonos\u00edtani a besz\u00e9d megjelen\u00e9s\u00e9t a hangfolyamban. <\/p>\n

A modellek k\u00e9t form\u00e1tumban k\u00e9sz\u00fcltek: angol nyelv\u0171 modell \u00e9s egy t\u00f6bbnyelv\u0171 modell, amely t\u00e1mogatja a orosz, ukr\u00e1n \u00e9s belorusz nyelveket is. Minden egyes forma 5 v\u00e1ltozatra oszlik, amelyek m\u00e9ret\u00fckben \u00e9s a modell \u00e1ltal lefedett param\u00e9terek sz\u00e1m\u00e1ban elt\u00e9rnek. Min\u00e9l nagyobb a m\u00e9ret, ann\u00e1l pontosabb \u00e9s magasabb min\u0151s\u00e9g\u0171 a felismer\u00e9s, de ann\u00e1l nagyobb videomem\u00f3ria-k\u00f6vetelm\u00e9ny is sz\u00fcks\u00e9ges, \u00e9s alacsonyabb teljes\u00edtm\u00e9nyszintet jelent. P\u00e9ld\u00e1ul a legkisebb v\u00e1ltozat 39 milli\u00f3 param\u00e9tert tartalmaz \u00e9s 1 GB videomem\u00f3ri\u00e1t ig\u00e9nyel, m\u00edg a legnagyobb 1550 milli\u00f3 param\u00e9tert foglal mag\u00e1ban \u00e9s 10 GB videomem\u00f3ri\u00e1t ig\u00e9nyel. A legkisebb v\u00e1ltozat 32-szer gyorsabb a legnagyobb v\u00e1ltozatn\u00e1l.

\"Megny\u00edlt<\/center> <\/p>\n

A rendszer a \"Transformer\" neur\u00e1lis h\u00e1l\u00f3zat architekt\u00far\u00e1j\u00e1t haszn\u00e1lja, amely egy k\u00f6lcs\u00f6nhat\u00e1sban l\u00e9v\u0151 k\u00f3dol\u00f3b\u00f3l \u00e9s dek\u00f3derb\u0151l \u00e1ll. A hang 30 m\u00e1sodperces szakaszokra van bontva, amelyeket log-Mel spektrum\u00e1 konvert\u00e1lnak, \u00e9s a k\u00f3dol\u00f3hoz tov\u00e1bb\u00edtanak. A k\u00f3dol\u00f3 munk\u00e1j\u00e1nak eredm\u00e9nye a dek\u00f3derhez ker\u00fcl, amely el\u0151rejelzi a sz\u00f6veges reprezent\u00e1ci\u00f3t, amely speci\u00e1lis tokencsoportokkal keveredik, lehet\u0151v\u00e9 t\u00e9ve egyetlen k\u00f6z\u00f6s modellben az olyan feladatok megold\u00e1s\u00e1t, mint a nyelv meghat\u00e1roz\u00e1sa, a kifejez\u00e9sek kiejt\u00e9s\u00e9nek id\u0151rendi nyilv\u00e1ntart\u00e1sa, a besz\u00e9d \u00e1t\u00edr\u00e1sa k\u00fcl\u00f6nb\u00f6z\u0151 nyelveken \u00e9s az angol nyelvre t\u00f6rt\u00e9n\u0151 ford\u00edt\u00e1s.
\n
Forr\u00e1s: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041f\u0440\u043e\u0435\u043a\u0442 OpenAI, \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0449\u0438\u0439\u0441\u044f \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435\u043c \u043e\u0431\u0449\u0435\u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b\u0445 \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u0432 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0433\u043e \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0430, \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b \u043d\u0430\u0440\u0430\u0431\u043e\u0442\u043a\u0438, \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0435 \u0441 \u0441\u0438\u0441\u0442\u0435\u043c\u043e\u0439 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438 Whisper. \u0423\u0442\u0432\u0435\u0440\u0436\u0434\u0430\u0435\u0442\u0441\u044f, \u0447\u0442\u043e \u0434\u043b\u044f \u0440\u0435\u0447\u0438 \u043d\u0430 \u0430\u043d\u0433\u043b\u0438\u0439\u0441\u043a\u043e\u043c \u044f\u0437\u044b\u043a\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u0430 \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0443\u0440\u043e\u0432\u043d\u0438 \u043d\u0430\u0434\u0451\u0436\u043d\u043e\u0441\u0442\u0438 \u0438 \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0431\u043b\u0438\u0437\u043a\u0438\u0435 \u043a \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044e \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u043e\u043c. \u041e\u0442\u043a\u0440\u044b\u0442\u044b \u043a\u043e\u0434 \u044d\u0442\u0430\u043b\u043e\u043d\u043d\u043e\u0439 \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0438 \u043d\u0430 \u0431\u0430\u0437\u0435 \u0444\u0440\u0435\u0439\u043c\u0432\u043e\u0440\u043a\u0430 PyTorch \u0438 \u043d\u0430\u0431\u043e\u0440 \u0443\u0436\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u043d\u044b\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439, \u0433\u043e\u0442\u043e\u0432\u044b\u0445 \u0434\u043b\u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u044f. \u041a\u043e\u0434 \u043e\u0442\u043a\u0440\u044b\u0442 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":105166,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-105165","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47A Whisper besz\u00e9dfelismer\u0151 \u00e9s ford\u00edt\u00f3 rendszer\u00e9nek k\u00f3dja nyilv\u00e1nos | ProHoster","description":"Az OpenAI projekt, amely nyilv\u00e1nos mesters\u00e9ges intelligencia projekteket fejleszt, k\u00f6zz\u00e9tette a Whisper besz\u00e9dfelismer\u0151 rendszer\u00e9vel kapcsolatos fejleszt\u00e9seit.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/news\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"hu_HU","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u041e\u0442\u043a\u0440\u044b\u0442 \u043a\u043e\u0434 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0438 \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u0430 \u0440\u0435\u0447\u0438 Whisper | ProHoster","og:description":"\u041f\u0440\u043e\u0435\u043a\u0442 OpenAI, \u0437\u0430\u043d\u0438\u043c\u0430\u044e\u0449\u0438\u0439\u0441\u044f \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435\u043c \u043e\u0431\u0449\u0435\u0434\u043e\u0441\u0442\u0443\u043f\u043d\u044b\u0445 \u043f\u0440\u043e\u0435\u043a\u0442\u043e\u0432 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0433\u043e \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0430, \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b \u043d\u0430\u0440\u0430\u0431\u043e\u0442\u043a\u0438, \u0441\u0432\u044f\u0437\u0430\u043d\u043d\u044b\u0435 \u0441 \u0441\u0438\u0441\u0442\u0435\u043c\u043e\u0439 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0440\u0435\u0447\u0438 Whisper.","og:url":"https:\/\/prohoster.info\/hu\/blog\/news\/otkryt-kod-sistemy-raspoznavaniya-i-perevoda-rechi-whisper","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2022-09-25T19:36:39+00:00","article:modified_time":"2022-09-25T19:36:39+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":[],"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/105165","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/comments?post=105165"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/105165\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media\/105166"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=105165"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=105165"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=105165"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}